{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lffd-a-light-and-fast-face-detector-for-edge","title":"LFFD: A Light and Fast Face Detector for Edge Devices","arxiv_id":"1904.10633","date":"2019-04-24","proceeding":null,"authors":["Yonghao He","Dezhong Xu","Lifang Wu","Meng Jian","Shiming Xiang","Chunhong Pan"],"abstract":"Face detection, as a fundamental technology for various applications, is always deployed on edge devices which have limited memory storage and low computing power. This paper introduces a Light and Fast Face Detector (LFFD) for edge devices. The proposed method is anchor-free and belongs to the one-stage category. Specifically, we rethink the importance of receptive field (RF) and effective receptive field (ERF) in the background of face detection. Essentially, the RFs of neurons in a certain layer are distributed regularly in the input image and theses RFs are natural \"anchors\". Combining RF \"anchors\" and appropriate RF strides, the proposed method can detect a large range of continuous face scales with 100% coverage in theory. The insightful understanding of relations between ERF and face scales motivates an efficient backbone for one-stage detection. The backbone is characterized by eight detection branches and common layers, resulting in efficient computation. Comprehensive and extensive experiments on popular benchmarks: WIDER FACE and FDDB are conducted. A new evaluation schema is proposed for application-oriented scenarios. Under the new schema, the proposed method can achieve superior accuracy (WIDER FACE Val/Test -- Easy: 0.910/0.896, Medium: 0.881/0.865, Hard: 0.780/0.770; FDDB -- discontinuous: 0.973, continuous: 0.724). Multiple hardware platforms are introduced to evaluate the running efficiency. The proposed method can obtain fast inference speed (NVIDIA TITAN Xp: 131.45 FPS at 640x480; NVIDIA TX2: 136.99 PFS at 160x120; Raspberry Pi 3 Model B+: 8.44 FPS at 160x120) with model size of 9 MB.","url_abs":"https://arxiv.org/abs/1904.10633v3","url_pdf":"https://arxiv.org/pdf/1904.10633v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/YonghaoHe/A-Light-and-Fast-Face-Detector-for-Edge-Devices","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/Qengineering/LFFD-MNN-Jetson-Nano","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/Qengineering/LFFD-MNN-Raspberry-Pi-4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/Qengineering/LFFD-ncnn-Jetson-Nano","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/Qengineering/LFFD-ncnn-Raspberry-Pi-4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/YonghaoHe/LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":null},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/aoru45/BasketNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/aoru45/LFFD-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/becauseofAI/lffd-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/borhanMorphy/fastface","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/borhanMorphy/light-face-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/donnyyou/pytorch-lffd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/jacke121/A-Light-and-Fast-Face-Detector-for-Edge-Devices","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/gouthamvgk/facemesh_coreml_tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"lffd-a-light-and-fast-face-detector-for-edge","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"raspberry-pi-3","task_name":"Raspberry Pi 3"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-detection-on-fddb","task":"Face Detection","dataset":"FDDB","model":"LFFD","rank_in_archive_order":6,"of":11,"metrics":{"AP":"0.973"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-easy","task":"Face Detection","dataset":"WIDER Face (Easy)","model":"LFFD","rank_in_archive_order":25,"of":27,"metrics":{"AP":"0.896"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"LFFD","rank_in_archive_order":30,"of":40,"metrics":{"AP":"0.770"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"LFFD","rank_in_archive_order":30,"of":37,"metrics":{"AP":"0.865"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.10633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10633"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/LFFD-MNN-Jetson-Nano","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/LFFD-MNN-Raspberry-Pi-4","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YonghaoHe/LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YonghaoHe/A-Light-and-Fast-Face-Detector-for-Edge-Devices","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aoru45/BasketNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/donnyyou/pytorch-lffd","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jacke121/A-Light-and-Fast-Face-Detector-for-Edge-Devices","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/LFFD-ncnn-Raspberry-Pi-4","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/borhanMorphy/light-face-detection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gouthamvgk/facemesh_coreml_tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/borhanMorphy/fastface","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aoru45/LFFD-Pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/becauseofAI/lffd-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/LFFD-ncnn-Jetson-Nano","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_fixture":1,"unverified":4},"by_repo_kind":{"listed":{"samples":5,"ran":1,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2e607d2f8085de1d","entry":"NMS","repo":"YonghaoHe/LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices","repo_kind":"listed","path":"face_detection/deploy_tensorrt/predict_tensorrt.py","file_url":"https://github.com/YonghaoHe/LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices/blob/HEAD/face_detection/deploy_tensorrt/predict_tensorrt.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e607d2f8085de1d"}},{"code_sha256_prefix":"5f4b78fc28e71491","entry":"conv1x1","repo":"becauseofAI/lffd-pytorch","repo_kind":"listed","path":"face_detection/net_farm/naivenet.py","file_url":"https://github.com/becauseofAI/lffd-pytorch/blob/HEAD/face_detection/net_farm/naivenet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f4b78fc28e71491"}},{"code_sha256_prefix":"eb23199a3b7b61cd","entry":"conv3x3","repo":"becauseofAI/lffd-pytorch","repo_kind":"listed","path":"face_detection/net_farm/naivenet.py","file_url":"https://github.com/becauseofAI/lffd-pytorch/blob/HEAD/face_detection/net_farm/naivenet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb23199a3b7b61cd"}},{"code_sha256_prefix":"2a39b678b1d2cff1","entry":"default_collate_fn","repo":"borhanMorphy/fastface","repo_kind":"listed","path":"fastface/dataset/base.py","file_url":"https://github.com/borhanMorphy/fastface/blob/HEAD/fastface/dataset/base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a39b678b1d2cff1"}},{"code_sha256_prefix":"32af7168a9d05be5","entry":"get_naivenet","repo":"becauseofAI/lffd-pytorch","repo_kind":"listed","path":"face_detection/net_farm/naivenet.py","file_url":"https://github.com/becauseofAI/lffd-pytorch/blob/HEAD/face_detection/net_farm/naivenet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32af7168a9d05be5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}